Report Summary
The Chair of the Scottish Police Authority launched a national conversation on the potential use of Live Facial Recognition (LFR) in Scotland in June 2024. This paper aims to provide a summary of the available information on the use of LFR in a policing context.
To access the full document please open the PDF document above.
To view as accessible content please use the sections below. (Note that tables and images are not available as accessible content).
Appendix D: National Physical Laboratory (NPL) review of MPS and SWP LFR technology
MPS and SWP use NEC Neoface V4 facial recognition software which has a 0.6 facial matching threshold. The threshold relates to how many aspects of the image captured and the image in the database are compared and the volume of matches between them required to result in a positive identification. Uses by MPS include “to prevent and detect crime, find wanted criminals, safeguard vulnerable people, and to protect people from harm”. SWP state they use LFR to “prevent and detect crime and help protect the vulnerable” ‑ see Box 2 for recent examples of LFR deployment.
True-Positive Identification Rate (TPIR) ‑ the rate of successful recognition when people on the watchlist pass through an area with LFR cameras.
False-Positive Identification Rate (FPIR) ‑ the rate of incorrect recognition (i.e., false positives or false alerts) when people not on the watchlist pass through an area with LFR cameras.
For a watch list containing 10,000 images (more in line with the size of MPS lists), there was a TPIR of 89% and a FPIR of 0.017 (1 in 6000). For a watch list containing 1,000 images (more in line with the size of SWP lists), there was a TPIR of 89% and a FPIR of 0.002 (1 in 60,000).
In relation to demographics (ethnicity, gender, age and height), it was found that:
- TPIR improved with age
- TPIR and FPIR at a face-matched threshold of 0.6 was equitable across gender and ethnicity groups.
- How crowded areas are where LFR cameras are in operation can impact TPIR in relation to height.
Examples of uses of LFR in policing in England and Wales from Home Office Police use of Facial Recognition: Factsheet
At the Arsenal v Tottenham north London derby on 24 September 2023, it led to three arrests, including a suspected sex offender.
A wanted sex offender was sent back to jail after being identified at the Coronation of King Charles. An image of his face matched that of a wanted suspect. He was arrested and sent back to prison for breaching the terms of his release.
Over two Friday nights in Soho in August 2023 the MPS used it to help find high harm offenders. Across the two deployments there were six accurate alerts and no false alerts. It led to the police engaging with six people, five of whom were arrested including a man wanted for possession of a bladed article and a woman wanted for breach of bail in relation to robbery.
This review concluded that the accuracy of LFR had significantly improved. The technology behind LFR, as with any new technology, continues to improve gradually in terms of accuracy and efficiency.
